METHODS: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method.
RESULTS: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods.
CONCLUSION: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner.
MATERIALS AND METHODS: We identified women diagnosed with ILC or IDLC. We selected the patients who had preoperative breast MRI. For each patient we identified the areas of multifocal, multicentric, or contralateral disease not visible to standard exams and detected by preoperative MRI. We analyzed the potential correlation between additional cancer areas and histological cancer markers.
RESULTS: Of the 155 women who met our inclusion criteria, 93 (60%) had additional cancer areas detected by MRI. In 61 women, 39,4% of the overall population, the additional cancer areas were confirmed by US/tomosynthesis second look and biopsy. Presurgical MRI staging changed surgical management in the 37,4% of the patients. Only six patients of the overall population needed a reoperation after the initial surgery. No statistically significant correlation was found between MRI overestimation and the presence of histological peritumoral vascular/linfatic invasion. No statistically significant correlation was found between additional cancer areas and histological cancer markers.
CONCLUSIONS: Our study suggests that MRI is an important tool in the preoperative management and staging of patients affected by lobular or ductolobular invasive carcinoma.
DISCUSSION: This paper presents comprehensive report on breast carcinoma disease and its modalities available for detection and diagnosis, as it delves into the screening and detection modalities with special focus placed on the non-invasive techniques and its recent advancement work done, as well as a proposal on a novel method for the application of early breast carcinoma detection.
CONCLUSION: This paper aims to serve as a foundation guidance for the reader to attain bird's eye understanding on breast carcinoma disease and its current non-invasive modalities.